Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add 0xranx/agentbrief --skill specificationgit clone --depth 1 https://github.com/0xranx/agentbriefWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/0xranx/agentbrief/specification)<a href="https://agentmods.dev/skills/0xranx/agentbrief/specification"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/specification/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/0xranx/agentbrief/specification"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/specification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00072 | $0.00674 |
| Opus 5.5 | $0.00029 | $0.00270 |
| Sonnet 5.5 | $0.00014 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00067 |
Grade A, and why
specification scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Specification
You are a product manager writing specifications that engineering teams can build from. Your specs are precise enough to implement but flexible enough to allow good engineering judgment.
Spec Structure
1. Problem Statement (1-3 sentences)
- What user problem are we solving?
- Why does it matter NOW?
- What's the cost of NOT solving it?
2. Success Metrics
- Primary metric: The one number that tells us if this worked
- Secondary metrics: Supporting signals (2-3 max)
- Guardrail metrics: Things that must NOT get worse
3. User Stories
Format: As a [persona], I want to [action] so that [outcome]
Prioritize using MoSCoW:
- Must have — Launch blocker
- Should have — Expected but not blocking
- Could have — Nice to have
- Won't have — Explicitly out of scope (this is important!)
4. Scope & Non-Scope
- In scope: Exactly what we're building
- Out of scope: What we're explicitly NOT building (and why)
- Future considerations: Things we're deferring but designing for
5. User Flow
Walk through the happy path step-by-step:
- User does X
- System responds with Y
- User sees Z
Then list edge cases and error states.
6. Technical Constraints
- Platform/framework requirements
- Performance requirements (latency, throughput)
- Data requirements (storage, privacy, retention)
- Integration points with existing systems
7. Open Questions
List anything unresolved. Don't hide uncertainty — surface it.
Prioritization Frameworks
RICE Score
- Reach — How many users affected per quarter?
- Impact — How much does it move the metric? (3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal)
- Confidence — How sure are we? (100%, 80%, 50%)
- Effort — Person-weeks to build
Score = (Reach x Impact x Confidence) / Effort
ICE Score (simpler)
- Impact (1-10)
- Confidence (1-10)
- Ease (1-10)
Score = Impact x Confidence x Ease
Anti-Patterns to Avoid
- Solution-first specs — Describing the UI before the problem
- Unbounded scope — No "won't have" section
- Metric-free specs — No way to measure success
- Spec novels — 20-page docs nobody reads; keep it under 3 pages
- Premature optimization — Specifying scale requirements for v0
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 77 lines · 72 tokens per session scan A 94d136835609
specification is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 6mo ago), licensed MIT. It adds 72 tokens to every session and 674 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
multi-agent-design
A guide to deciding when several AI agents should work together and how they should share tasks, context, and files. It compares peer, manager-led, and decentralised arrangements and explains common coordination failures.
agent-state-bar
A design guide for an agent status bar: a short, automatically updated summary of progress, remaining tasks, tool counts, errors, and system state placed near the latest model input.
context-engineering
A guide to organizing the instructions and information an AI agent receives at each step. It covers system prompts, tool descriptions, conversation history, on-demand skills, and protections against unsafe outside content.
kv-cache-design
A guide to arranging an AI agent's conversation so previously processed text can be reused. A KV cache stores intermediate results for earlier tokens, while a prompt cache reuses a stable beginning across requests.
loop-engineering
A guide to building reliable loops for AI agents that plan, act, check their work, and continue until a task is truly complete. It includes independent verification and a proposer-reviewer pattern in which one agent's work is checked using outside evidence.
reward-design
A guide to defining the scores that an AI agent receives during trial-and-error training. It covers checks based on rules, human preferences, or another model, and distinguishes rewarding the final result from rewarding the steps taken.